Combining dynamic <scp>XFEM</scp> with machine learning for detection of multiple flaws

Jiang, Shouyan; Zhao, Linxin; Du, Chengbin

doi:10.1002/nme.6791

Cited by 16 publications

(3 citation statements)

References 52 publications

(91 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In paper, 145 a novel methodology for multiple flaw detection is presented, combining the dynamic XFEM with the extreme learning machine (ELM) for modeling and prediction. The XFEM is employed to overcome the issues associated with the large quantity of input data required for ELM network training, whereas the ELM itself is used to bypass the time‐consuming analyses commonly used for multiple flaw detection.…”

Section: Literature Overviewmentioning

confidence: 99%

Fatigue crack growth simulation by extended finite element method: A review of case studies

Sedmak

2024

Fatigue Fract Eng Mat Struct

View full text Add to dashboard Cite

Numerical simulation of fatigue crack growth (FCG) is presented, based on the application of the extended finite element method (XFEM). Couple of case studies are presented, as a review of recent experience of the Belgrade school of XFEM simulations, established at the Faculty of Mechanical Engineering. Case studies comprised Charpy specimen with initial crack at the notch tip, oil rig pipe with an axial surface crack, pressure vessels with a crack at the welded joint with connecting pipe, turbine shaft with a crack at the transition radius, optimization of a wing spar in respect to FCG, the effect of mesh size on fatigue life estimation of a stringer panel, fatigue life estimation of wing‐to‐fuselage connecting lug, geometry effect on fatigue life of orthopedic plates and fatigue life of hip implant. Based on these case studies, XFEM is discussed in respect to its accuracy and efficiency. It is concluded that XFEM is a versatile tool for simulation of FCG, providing an excellent option for precise and reliable fatigue life of a cracked component.

show abstract

Section: Literature Overviewmentioning

confidence: 99%

Fatigue crack growth simulation by extended finite element method: A review of case studies

Sedmak

2024

Fatigue Fract Eng Mat Struct

View full text Add to dashboard Cite

show abstract

“…Some interesting works have been reported using physical signals, such as sound wave, electromagnetic wave, and temperature, which are adapted to identify structural defect and damage. [18][19][20] Here, because machining-induced plasticity behavior is highly nonlinear and has multifield coupling characteristics, traditional machine learning methods are difficult to accurately describe or predict its complex evolution process. Hence, considering its powerful data-driven and physical constraint ability, PIML strategy is adopted to investigate the machining-induced plasticity behavior for achieving fast and accurate prediction of dislocation behaviors and optimizing machining parameters with good validity and interpretability.…”

Section: Introductionmentioning

confidence: 99%

Physics‐Informed Multistage Machine Learning Strategy for the Nanomachining‐Induced Plastic Deformation Behavior

Xie

Peng

et al. 2023

Adv Eng Mater

View full text Add to dashboard Cite

The evolution of the dislocation density induced by the nanomachining process dominates the plastic deformation behaviors of materials, thus affecting the mechanical properties significantly. However, a challenging topic related to how to establish an accurate model for predicting the dislocation density based on the limited simulations and experiments arises due to the complicated thermal–mechanical coupling mechanism during the machining process. Herein, a multistage method integrating machine learning, physics, and high‐throughput atomic simulation is proposed to investigate the effect of cutting speed on the dislocation behavior in polycrystal copper. Compared with the traditional one‐step machine learning method, the constraint of physical features effectively improves the accuracy and generalization ability of the model. The results indicate that the dislocation behaviors depend on the competition between the cutting force and temperature. In the low‐cutting speed, the predominated role of the cutting temperature leads to a rapid decline of the dislocation density. In contrast, the dislocation density tends to be stable under a high‐speed cutting process due to the dynamic balance between the effects of the cutting force and temperature. Notably, the proposed strategy provides a new and universal framework to design the machining parameters to obtain high‐quality products.

show abstract

“…Its theories and methods have been widely applied to solve complex problems (especially those of classification and regression) in engineering and applied science. [30][31][32] Jiang et al 33 proposed a novel methodology by combining the dynamic extended finite element method with machine learning for multiple void-like flaw detection; in this method, the extreme learning machine was chosen as a learning rule for modeling and prediction according to the structural frequencies and displacement mode shapes reflecting the positions and dimensions of flaws. de Assis et al 34 solved an inverse crack identification problem using metaheuristic sunflower optimization, artificial neural networks, and the response surface method.…”

Section: Introductionmentioning

confidence: 99%

Flaw classification and detection in thin‐plate structures based on scaled boundary finite element method and deep learning

Jiang

Chen

Sun

et al. 2022

Numerical Meth Engineering

Self Cite

View full text Add to dashboard Cite

The identification of internal structural flaws is an important research topic in structural health monitoring. At present, structural safety inspections based on nondestructive testing procedures mainly focus on qualitative analysis; hence, it is difficult to identify the scale of flaws quantitatively. In this article, an inversion model that can realize quantitative detection is proposed by combing the scaled boundary finite element method (SBFEM) with deep learning. First, the lamb wave propagation processes in thin structures containing flaws were simulated using the SBFEM, and the echo wave signal at an observation point was recorded and paired with the flaw information. Then, the paired SBFEM datasets were used to train the deep learning model employing a convolutional neural network. A flaw classification and identification model based on SBFEM datasets was established. For a thin structure with unknown flaw information, and by using the measured observation point signals, the established deep learning model can predict flaw information in real time. Finally, the model performance was verified using several numerical examples. The results show that the proposed model can accurately predict flaw information and is robust against noise; thus, it offers an advantage over existing nondestructive testing procedures and a development in the field of structural health monitoring.

show abstract

Combining dynamic XFEM with machine learning for detection of multiple flaws

Cited by 16 publications

References 52 publications

Fatigue crack growth simulation by extended finite element method: A review of case studies

Fatigue crack growth simulation by extended finite element method: A review of case studies

Physics‐Informed Multistage Machine Learning Strategy for the Nanomachining‐Induced Plastic Deformation Behavior

Flaw classification and detection in thin‐plate structures based on scaled boundary finite element method and deep learning

Contact Info

Product

Resources

About